© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39016
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¸Ĥ
    -0.30
    æĬĢæľ¯
    -0.26
    0
    -0.26
    1
    -0.26
    -way
    -0.26
    2
    -0.26
    -
    -0.26
    æĬĢèĥ½
    -0.25
    ç§ijæĬĢ
    -0.25
     world
    -0.25
    POSITIVE LOGITS
    çĮĽçĦ¶
    0.37
    æ´»ä¸ĭåİ»
    0.31
    ä¼ļè§īå¾Ĺ
    0.30
    æľīæľŁ
    0.30
    让人们
    0.30
    好ä¸į容æĺĵ
    0.29
    åģ·åģ·
    0.29
    就好åĥı
    0.29
    å°±å¦ĤåIJĮ
    0.29
     __________________↵↵
    0.28
    Activations Density 2.824%

    No Known Activations

    This feature has no known activations.